diff options
33 files changed, 609 insertions, 270 deletions
diff --git a/Documentation/core-api/xarray.rst b/Documentation/core-api/xarray.rst index fcedc5349ace..640934b6f7b4 100644 --- a/Documentation/core-api/xarray.rst +++ b/Documentation/core-api/xarray.rst @@ -25,10 +25,6 @@ good performance with large indices. If your index can be larger than ``ULONG_MAX`` then the XArray is not the data type for you. The most important user of the XArray is the page cache. -Each non-``NULL`` entry in the array has three bits associated with -it called marks. Each mark may be set or cleared independently of -the others. You can iterate over entries which are marked. - Normal pointers may be stored in the XArray directly. They must be 4-byte aligned, which is true for any pointer returned from kmalloc() and alloc_page(). It isn't true for arbitrary user-space pointers, @@ -41,12 +37,11 @@ When you retrieve an entry from the XArray, you can check whether it is a value entry by calling xa_is_value(), and convert it back to an integer by calling xa_to_value(). -Some users want to store tagged pointers instead of using the marks -described above. They can call xa_tag_pointer() to create an -entry with a tag, xa_untag_pointer() to turn a tagged entry -back into an untagged pointer and xa_pointer_tag() to retrieve -the tag of an entry. Tagged pointers use the same bits that are used -to distinguish value entries from normal pointers, so each user must +Some users want to tag the pointers they store in the XArray. You can +call xa_tag_pointer() to create an entry with a tag, xa_untag_pointer() +to turn a tagged entry back into an untagged pointer and xa_pointer_tag() +to retrieve the tag of an entry. Tagged pointers use the same bits that +are used to distinguish value entries from normal pointers, so you must decide whether they want to store value entries or tagged pointers in any particular XArray. @@ -56,10 +51,9 @@ conflict with value entries or internal entries. An unusual feature of the XArray is the ability to create entries which occupy a range of indices. Once stored to, looking up any index in the range will return the same entry as looking up any other index in -the range. Setting a mark on one index will set it on all of them. -Storing to any index will store to all of them. Multi-index entries can -be explicitly split into smaller entries, or storing ``NULL`` into any -entry will cause the XArray to forget about the range. +the range. Storing to any index will store to all of them. Multi-index +entries can be explicitly split into smaller entries, or storing ``NULL`` +into any entry will cause the XArray to forget about the range. Normal API ========== @@ -87,17 +81,11 @@ If you want to only store a new entry to an index if the current entry at that index is ``NULL``, you can use xa_insert() which returns ``-EBUSY`` if the entry is not empty. -You can enquire whether a mark is set on an entry by using -xa_get_mark(). If the entry is not ``NULL``, you can set a mark -on it by using xa_set_mark() and remove the mark from an entry by -calling xa_clear_mark(). You can ask whether any entry in the -XArray has a particular mark set by calling xa_marked(). - You can copy entries out of the XArray into a plain array by calling -xa_extract(). Or you can iterate over the present entries in -the XArray by calling xa_for_each(). You may prefer to use -xa_find() or xa_find_after() to move to the next present -entry in the XArray. +xa_extract(). Or you can iterate over the present entries in the XArray +by calling xa_for_each(), xa_for_each_start() or xa_for_each_range(). +You may prefer to use xa_find() or xa_find_after() to move to the next +present entry in the XArray. Calling xa_store_range() stores the same entry in a range of indices. If you do this, some of the other operations will behave @@ -124,6 +112,31 @@ xa_destroy(). If the XArray entries are pointers, you may wish to free the entries first. You can do this by iterating over all present entries in the XArray using the xa_for_each() iterator. +Search Marks +------------ + +Each entry in the array has three bits associated with it called marks. +Each mark may be set or cleared independently of the others. You can +iterate over marked entries by using the xa_for_each_marked() iterator. + +You can enquire whether a mark is set on an entry by using +xa_get_mark(). If the entry is not ``NULL``, you can set a mark on it +by using xa_set_mark() and remove the mark from an entry by calling +xa_clear_mark(). You can ask whether any entry in the XArray has a +particular mark set by calling xa_marked(). Erasing an entry from the +XArray causes all marks associated with that entry to be cleared. + +Setting or clearing a mark on any index of a multi-index entry will +affect all indices covered by that entry. Querying the mark on any +index will return the same result. + +There is no way to iterate over entries which are not marked; the data +structure does not allow this to be implemented efficiently. There are +not currently iterators to search for logical combinations of bits (eg +iterate over all entries which have both ``XA_MARK_1`` and ``XA_MARK_2`` +set, or iterate over all entries which have ``XA_MARK_0`` or ``XA_MARK_2`` +set). It would be possible to add these if a user arises. + Allocating XArrays ------------------ @@ -180,6 +193,8 @@ No lock needed: Takes RCU read lock: * xa_load() * xa_for_each() + * xa_for_each_start() + * xa_for_each_range() * xa_find() * xa_find_after() * xa_extract() @@ -419,10 +434,9 @@ you last processed. If you have interrupts disabled while iterating, then it is good manners to pause the iteration and reenable interrupts every ``XA_CHECK_SCHED`` entries. -The xas_get_mark(), xas_set_mark() and -xas_clear_mark() functions require the xa_state cursor to have -been moved to the appropriate location in the xarray; they will do -nothing if you have called xas_pause() or xas_set() +The xas_get_mark(), xas_set_mark() and xas_clear_mark() functions require +the xa_state cursor to have been moved to the appropriate location in the +XArray; they will do nothing if you have called xas_pause() or xas_set() immediately before. You can call xas_set_update() to have a callback function diff --git a/drivers/hwmon/adt7475.c b/drivers/hwmon/adt7475.c index 6c64d50c9aae..01c2eeb02aa9 100644 --- a/drivers/hwmon/adt7475.c +++ b/drivers/hwmon/adt7475.c @@ -294,9 +294,10 @@ static inline u16 volt2reg(int channel, long volt, u8 bypass_attn) long reg; if (bypass_attn & (1 << channel)) - reg = (volt * 1024) / 2250; + reg = DIV_ROUND_CLOSEST(volt * 1024, 2250); else - reg = (volt * r[1] * 1024) / ((r[0] + r[1]) * 2250); + reg = DIV_ROUND_CLOSEST(volt * r[1] * 1024, + (r[0] + r[1]) * 2250); return clamp_val(reg, 0, 1023) & (0xff << 2); } diff --git a/drivers/hwmon/hwmon.c b/drivers/hwmon/hwmon.c index 1f3b30b085b9..d018b20089ec 100644 --- a/drivers/hwmon/hwmon.c +++ b/drivers/hwmon/hwmon.c @@ -51,6 +51,7 @@ struct hwmon_device_attribute { #define to_hwmon_attr(d) \ container_of(d, struct hwmon_device_attribute, dev_attr) +#define to_dev_attr(a) container_of(a, struct device_attribute, attr) /* * Thermal zone information @@ -58,7 +59,7 @@ struct hwmon_device_attribute { * also provides the sensor index. */ struct hwmon_thermal_data { - struct hwmon_device *hwdev; /* Reference to hwmon device */ + struct device *dev; /* Reference to hwmon device */ int index; /* sensor index */ }; @@ -95,9 +96,27 @@ static const struct attribute_group *hwmon_dev_attr_groups[] = { NULL }; +static void hwmon_free_attrs(struct attribute **attrs) +{ + int i; + + for (i = 0; attrs[i]; i++) { + struct device_attribute *dattr = to_dev_attr(attrs[i]); + struct hwmon_device_attribute *hattr = to_hwmon_attr(dattr); + + kfree(hattr); + } + kfree(attrs); +} + static void hwmon_dev_release(struct device *dev) { - kfree(to_hwmon_device(dev)); + struct hwmon_device *hwdev = to_hwmon_device(dev); + + if (hwdev->group.attrs) + hwmon_free_attrs(hwdev->group.attrs); + kfree(hwdev->groups); + kfree(hwdev); } static struct class hwmon_class = { @@ -119,11 +138,11 @@ static DEFINE_IDA(hwmon_ida); static int hwmon_thermal_get_temp(void *data, int *temp) { struct hwmon_thermal_data *tdata = data; - struct hwmon_device *hwdev = tdata->hwdev; + struct hwmon_device *hwdev = to_hwmon_device(tdata->dev); int ret; long t; - ret = hwdev->chip->ops->read(&hwdev->dev, hwmon_temp, hwmon_temp_input, + ret = hwdev->chip->ops->read(tdata->dev, hwmon_temp, hwmon_temp_input, tdata->index, &t); if (ret < 0) return ret; @@ -137,8 +156,7 @@ static const struct thermal_zone_of_device_ops hwmon_thermal_ops = { .get_temp = hwmon_thermal_get_temp, }; -static int hwmon_thermal_add_sensor(struct device *dev, - struct hwmon_device *hwdev, int index) +static int hwmon_thermal_add_sensor(struct device *dev, int index) { struct hwmon_thermal_data *tdata; struct thermal_zone_device *tzd; @@ -147,10 +165,10 @@ static int hwmon_thermal_add_sensor(struct device *dev, if (!tdata) return -ENOMEM; - tdata->hwdev = hwdev; + tdata->dev = dev; tdata->index = index; - tzd = devm_thermal_zone_of_sensor_register(&hwdev->dev, index, tdata, + tzd = devm_thermal_zone_of_sensor_register(dev, index, tdata, &hwmon_thermal_ops); /* * If CONFIG_THERMAL_OF is disabled, this returns -ENODEV, @@ -162,8 +180,7 @@ static int hwmon_thermal_add_sensor(struct device *dev, return 0; } #else -static int hwmon_thermal_add_sensor(struct device *dev, - struct hwmon_device *hwdev, int index) +static int hwmon_thermal_add_sensor(struct device *dev, int index) { return 0; } @@ -250,8 +267,7 @@ static bool is_string_attr(enum hwmon_sensor_types type, u32 attr) (type == hwmon_fan && attr == hwmon_fan_label); } -static struct attribute *hwmon_genattr(struct device *dev, - const void *drvdata, +static struct attribute *hwmon_genattr(const void *drvdata, enum hwmon_sensor_types type, u32 attr, int index, @@ -279,7 +295,7 @@ static struct attribute *hwmon_genattr(struct device *dev, if ((mode & 0222) && !ops->write) return ERR_PTR(-EINVAL); - hattr = devm_kzalloc(dev, sizeof(*hattr), GFP_KERNEL); + hattr = kzalloc(sizeof(*hattr), GFP_KERNEL); if (!hattr) return ERR_PTR(-ENOMEM); @@ -492,8 +508,7 @@ static int hwmon_num_channel_attrs(const struct hwmon_channel_info *info) return n; } -static int hwmon_genattrs(struct device *dev, - const void *drvdata, +static int hwmon_genattrs(const void *drvdata, struct attribute **attrs, const struct hwmon_ops *ops, const struct hwmon_channel_info *info) @@ -519,7 +534,7 @@ static int hwmon_genattrs(struct device *dev, attr_mask &= ~BIT(attr); if (attr >= template_size) return -EINVAL; - a = hwmon_genattr(dev, drvdata, info->type, attr, i, + a = hwmon_genattr(drvdata, info->type, attr, i, templates[attr], ops); if (IS_ERR(a)) { if (PTR_ERR(a) != -ENOENT) @@ -533,8 +548,7 @@ static int hwmon_genattrs(struct device *dev, } static struct attribute ** -__hwmon_create_attrs(struct device *dev, const void *drvdata, - const struct hwmon_chip_info *chip) +__hwmon_create_attrs(const void *drvdata, const struct hwmon_chip_info *chip) { int ret, i, aindex = 0, nattrs = 0; struct attribute **attrs; @@ -545,15 +559,17 @@ __hwmon_create_attrs(struct device *dev, const void *drvdata, if (nattrs == 0) return ERR_PTR(-EINVAL); - attrs = devm_kcalloc(dev, nattrs + 1, sizeof(*attrs), GFP_KERNEL); + attrs = kcalloc(nattrs + 1, sizeof(*attrs), GFP_KERNEL); if (!attrs) return ERR_PTR(-ENOMEM); for (i = 0; chip->info[i]; i++) { - ret = hwmon_genattrs(dev, drvdata, &attrs[aindex], chip->ops, + ret = hwmon_genattrs(drvdata, &attrs[aindex], chip->ops, chip->info[i]); - if (ret < 0) + if (ret < 0) { + hwmon_free_attrs(attrs); return ERR_PTR(ret); + } aindex += ret; } @@ -595,14 +611,13 @@ __hwmon_device_register(struct device *dev, const char *name, void *drvdata, for (i = 0; groups[i]; i++) ngroups++; - hwdev->groups = devm_kcalloc(dev, ngroups, sizeof(*groups), - GFP_KERNEL); + hwdev->groups = kcalloc(ngroups, sizeof(*groups), GFP_KERNEL); if (!hwdev->groups) { err = -ENOMEM; goto free_hwmon; } - attrs = __hwmon_create_attrs(dev, drvdata, chip); + attrs = __hwmon_create_attrs(drvdata, chip); if (IS_ERR(attrs)) { err = PTR_ERR(attrs); goto free_hwmon; @@ -647,8 +662,7 @@ __hwmon_device_register(struct device *dev, const char *name, void *drvdata, hwmon_temp_input, j)) continue; if (info[i]->config[j] & HWMON_T_INPUT) { - err = hwmon_thermal_add_sensor(dev, - hwdev, j); + err = hwmon_thermal_add_sensor(hdev, j); if (err) { device_unregister(hdev); /* @@ -667,7 +681,7 @@ __hwmon_device_register(struct device *dev, const char *name, void *drvdata, return hdev; free_hwmon: - kfree(hwdev); + hwmon_dev_release(hdev); ida_remove: ida_simple_remove(&hwmon_ida, id); return ERR_PTR(err); diff --git a/drivers/hwmon/nct7802.c b/drivers/hwmon/nct7802.c index f3dd2a17bd42..2e97e56c72c7 100644 --- a/drivers/hwmon/nct7802.c +++ b/drivers/hwmon/nct7802.c @@ -23,8 +23,8 @@ static const u8 REG_VOLTAGE[5] = { 0x09, 0x0a, 0x0c, 0x0d, 0x0e }; static const u8 REG_VOLTAGE_LIMIT_LSB[2][5] = { - { 0x40, 0x00, 0x42, 0x44, 0x46 }, - { 0x3f, 0x00, 0x41, 0x43, 0x45 }, + { 0x46, 0x00, 0x40, 0x42, 0x44 }, + { 0x45, 0x00, 0x3f, 0x41, 0x43 }, }; static const u8 REG_VOLTAGE_LIMIT_MSB[5] = { 0x48, 0x00, 0x47, 0x47, 0x48 }; @@ -58,6 +58,8 @@ static const u8 REG_VOLTAGE_LIMIT_MSB_SHIFT[2][5] = { struct nct7802_data { struct regmap *regmap; struct mutex access_lock; /* for multi-byte read and write operations */ + u8 in_status; + struct mutex in_alarm_lock; }; static ssize_t temp_type_show(struct device *dev, @@ -368,6 +370,66 @@ static ssize_t in_store(struct device *dev, struct device_attribute *attr, return err ? : count; } +static ssize_t in_alarm_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct sensor_device_attribute_2 *sattr = to_sensor_dev_attr_2(attr); + struct nct7802_data *data = dev_get_drvdata(dev); + int volt, min, max, ret; + unsigned int val; + + mutex_lock(&data->in_alarm_lock); + + /* + * The SMI Voltage status register is the only register giving a status + * for voltages. A bit is set for each input crossing a threshold, in + * both direction, but the "inside" or "outside" limits info is not + * available. Also this register is cleared on read. + * Note: this is not explicitly spelled out in the datasheet, but + * from experiment. + * To deal with this we use a status cache with one validity bit and + * one status bit for each input. Validity is cleared at startup and + * each time the register reports a change, and the status is processed + * by software based on current input value and limits. + */ + ret = regmap_read(data->regmap, 0x1e, &val); /* SMI Voltage status */ + if (ret < 0) + goto abort; + + /* invalidate cached status for all inputs crossing a threshold */ + data->in_status &= ~((val & 0x0f) << 4); + + /* if cached status for requested input is invalid, update it */ + if (!(data->in_status & (0x10 << sattr->index))) { + ret = nct7802_read_voltage(data, sattr->nr, 0); + if (ret < 0) + goto abort; + volt = ret; + + ret = nct7802_read_voltage(data, sattr->nr, 1); + if (ret < 0) + goto abort; + min = ret; + + ret = nct7802_read_voltage(data, sattr->nr, 2); + if (ret < 0) + goto abort; + max = ret; + + if (volt < min || volt > max) + data->in_status |= (1 << sattr->index); + else + data->in_status &= ~(1 << sattr->index); + + data->in_status |= 0x10 << sattr->index; + } + + ret = sprintf(buf, "%u\n", !!(data->in_status & (1 << sattr->index))); +abort: + mutex_unlock(&data->in_alarm_lock); + return ret; +} + static ssize_t temp_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -660,7 +722,7 @@ static const struct attribute_group nct7802_temp_group = { static SENSOR_DEVICE_ATTR_2_RO(in0_input, in, 0, 0); static SENSOR_DEVICE_ATTR_2_RW(in0_min, in, 0, 1); static SENSOR_DEVICE_ATTR_2_RW(in0_max, in, 0, 2); -static SENSOR_DEVICE_ATTR_2_RO(in0_alarm, alarm, 0x1e, 3); +static SENSOR_DEVICE_ATTR_2_RO(in0_alarm, in_alarm, 0, 3); static SENSOR_DEVICE_ATTR_2_RW(in0_beep, beep, 0x5a, 3); static SENSOR_DEVICE_ATTR_2_RO(in1_input, in, 1, 0); @@ -668,19 +730,19 @@ static SENSOR_DEVICE_ATTR_2_RO(in1_input, in, 1, 0); static SENSOR_DEVICE_ATTR_2_RO(in2_input, in, 2, 0); static SENSOR_DEVICE_ATTR_2_RW(in2_min, in, 2, 1); static SENSOR_DEVICE_ATTR_2_RW(in2_max, in, 2, 2); -static SENSOR_DEVICE_ATTR_2_RO(in2_alarm, alarm, 0x1e, 0); +static SENSOR_DEVICE_ATTR_2_RO(in2_alarm, in_alarm, 2, 0); static SENSOR_DEVICE_ATTR_2_RW(in2_beep, beep, 0x5a, 0); static SENSOR_DEVICE_ATTR_2_RO(in3_input, in, 3, 0); static SENSOR_DEVICE_ATTR_2_RW(in3_min, in, 3, 1); static SENSOR_DEVICE_ATTR_2_RW(in3_max, in, 3, 2); -static SENSOR_DEVICE_ATTR_2_RO(in3_alarm, alarm, 0x1e, 1); +static SENSOR_DEVICE_ATTR_2_RO(in3_alarm, in_alarm, 3, 1); static SENSOR_DEVICE_ATTR_2_RW(in3_beep, beep, 0x5a, 1); static SENSOR_DEVICE_ATTR_2_RO(in4_input, in, 4, 0); static SENSOR_DEVICE_ATTR_2_RW(in4_min, in, 4, 1); static SENSOR_DEVICE_ATTR_2_RW(in4_max, in, 4, 2); -static SENSOR_DEVICE_ATTR_2_RO(in4_alarm, alarm, 0x1e, 2); +static SENSOR_DEVICE_ATTR_2_RO(in4_alarm, in_alarm, 4, 2); static SENSOR_DEVICE_ATTR_2_RW(in4_beep, beep, 0x5a, 2); static struct attribute *nct7802_in_attrs[] = { @@ -1011,6 +1073,7 @@ static int nct7802_probe(struct i2c_client *client, return PTR_ERR(data->regmap); mutex_init(&data->access_lock); + mutex_init(&data->in_alarm_lock); ret = nct7802_init_chip(data); if (ret < 0) diff --git a/drivers/leds/leds-as3645a.c b/drivers/leds/leds-as3645a.c index b7e0ae1af8fa..e8922fa03379 100644 --- a/drivers/leds/leds-as3645a.c +++ b/drivers/leds/leds-as3645a.c @@ -493,16 +493,17 @@ static int as3645a_parse_node(struct as3645a *flash, switch (id) { case AS_LED_FLASH: flash->flash_node = child; + fwnode_handle_get(child); break; case AS_LED_INDICATOR: flash->indicator_node = child; + fwnode_handle_get(child); break; default: dev_warn(&flash->client->dev, "unknown LED %u encountered, ignoring\n", id); break; } - fwnode_handle_get(child); } if (!flash->flash_node) { diff --git a/drivers/leds/leds-gpio.c b/drivers/leds/leds-gpio.c index a5c73f3d5f79..2bf74595610f 100644 --- a/drivers/leds/leds-gpio.c +++ b/drivers/leds/leds-gpio.c @@ -151,9 +151,14 @@ static struct gpio_leds_priv *gpio_leds_create(struct platform_device *pdev) struct gpio_led led = {}; const char *state = NULL; + /* + * Acquire gpiod from DT with uninitialized label, which + * will be updated after LED class device is registered, + * Only then the final LED name is known. + */ led.gpiod = devm_fwnode_get_gpiod_from_child(dev, NULL, child, GPIOD_ASIS, - led.name); + NULL); if (IS_ERR(led.gpiod)) { fwnode_handle_put(child); return ERR_CAST(led.gpiod); @@ -186,6 +191,9 @@ static struct gpio_leds_priv *gpio_leds_create(struct platform_device *pdev) fwnode_handle_put(child); return ERR_PTR(ret); } + /* Set gpiod label to match the corresponding LED name. */ + gpiod_set_consumer_name(led_dat->gpiod, + led_dat->cdev.dev->kobj.name); priv->num_leds++; } diff --git a/drivers/leds/leds-lm3532.c b/drivers/leds/leds-lm3532.c index 0507c6575c08..491268bb34a7 100644 --- a/drivers/leds/leds-lm3532.c +++ b/drivers/leds/leds-lm3532.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 // TI LM3532 LED driver // Copyright (C) 2019 Texas Instruments Incorporated - http://www.ti.com/ +// http://www.ti.com/lit/ds/symlink/lm3532.pdf #include <linux/i2c.h> #include <linux/leds.h> @@ -623,7 +624,7 @@ static int lm3532_parse_node(struct lm3532_data *priv) led->num_leds = fwnode_property_count_u32(child, "led-sources"); if (led->num_leds > LM3532_MAX_LED_STRINGS) { - dev_err(&priv->client->dev, "To many LED string defined\n"); + dev_err(&priv->client->dev, "Too many LED string defined\n"); continue; } diff --git a/drivers/leds/leds-max77650.c b/drivers/leds/leds-max77650.c index 4c2d0b3c6dad..a0d4b725c917 100644 --- a/drivers/leds/leds-max77650.c +++ b/drivers/leds/leds-max77650.c @@ -135,9 +135,16 @@ err_node_put: return rv; } +static const struct of_device_id max77650_led_of_match[] = { + { .compatible = "maxim,max77650-led" }, + { } +}; +MODULE_DEVICE_TABLE(of, max77650_led_of_match); + static struct platform_driver max77650_led_driver = { .driver = { .name = "max77650-led", + .of_match_table = max77650_led_of_match, }, .probe = max77650_led_probe, }; diff --git a/drivers/leds/leds-rb532.c b/drivers/leds/leds-rb532.c index db5af83f0cec..b6447c1721b4 100644 --- a/drivers/leds/leds-rb532.c +++ b/drivers/leds/leds-rb532.c @@ -21,7 +21,6 @@ static void rb532_led_set(struct led_classdev *cdev, { if (brightness) set_latch_u5(LO_ULED, 0); - else set_latch_u5(0, LO_ULED); } diff --git a/drivers/leds/trigger/ledtrig-pattern.c b/drivers/leds/trigger/ledtrig-pattern.c index 718729c89440..3abcafe46278 100644 --- a/drivers/leds/trigger/ledtrig-pattern.c +++ b/drivers/leds/trigger/ledtrig-pattern.c @@ -455,7 +455,7 @@ static void __exit pattern_trig_exit(void) module_init(pattern_trig_init); module_exit(pattern_trig_exit); -MODULE_AUTHOR("Raphael Teysseyre <[email protected]"); -MODULE_AUTHOR("Baolin Wang <[email protected]"); +MODULE_AUTHOR("Raphael Teysseyre <[email protected]>"); +MODULE_AUTHOR("Baolin Wang <[email protected]>"); MODULE_DESCRIPTION("LED Pattern trigger"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/mmc/host/sdhci-tegra.c b/drivers/mmc/host/sdhci-tegra.c index 7bc950520fd9..403ac44a7378 100644 --- a/drivers/mmc/host/sdhci-tegra.c +++ b/drivers/mmc/host/sdhci-tegra.c @@ -386,7 +386,7 @@ static void tegra_sdhci_reset(struct sdhci_host *host, u8 mask) misc_ctrl |= SDHCI_MISC_CTRL_ENABLE_DDR50; if (soc_data->nvquirks & NVQUIRK_ENABLE_SDR104) misc_ctrl |= SDHCI_MISC_CTRL_ENABLE_SDR104; - if (soc_data->nvquirks & SDHCI_MISC_CTRL_ENABLE_SDR50) + if (soc_data->nvquirks & NVQUIRK_ENABLE_SDR50) clk_ctrl |= SDHCI_CLOCK_CTRL_SDR50_TUNING_OVERRIDE; } diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c index 1b1c26da3fe0..659a9459ace3 100644 --- a/drivers/mmc/host/sdhci.c +++ b/drivers/mmc/host/sdhci.c @@ -3913,11 +3913,13 @@ int sdhci_setup_host(struct sdhci_host *host) if (host->ops->get_min_clock) mmc->f_min = host->ops->get_min_clock(host); else if (host->version >= SDHCI_SPEC_300) { - if (host->clk_mul) { - mmc->f_min = (host->max_clk * host->clk_mul) / 1024; + if (host->clk_mul) max_clk = host->max_clk * host->clk_mul; - } else - mmc->f_min = host->max_clk / SDHCI_MAX_DIV_SPEC_300; + /* + * Divided Clock Mode minimum clock rate is always less than + * Programmable Clock Mode minimum clock rate. + */ + mmc->f_min = host->max_clk / SDHCI_MAX_DIV_SPEC_300; } else mmc->f_min = host->max_clk / SDHCI_MAX_DIV_SPEC_200; diff --git a/drivers/mmc/host/sdhci_am654.c b/drivers/mmc/host/sdhci_am654.c index b8e897e31e2e..b8fe94fd9525 100644 --- a/drivers/mmc/host/sdhci_am654.c +++ b/drivers/mmc/host/sdhci_am654.c @@ -240,6 +240,35 @@ static void sdhci_am654_write_b(struct sdhci_host *host, u8 val, int reg) writeb(val, host->ioaddr + reg); } +static int sdhci_am654_execute_tuning(struct mmc_host *mmc, u32 opcode) +{ + struct sdhci_host *host = mmc_priv(mmc); + int err = sdhci_execute_tuning(mmc, opcode); + + if (err) + return err; + /* + * Tuning data remains in the buffer after tuning. + * Do a command and data reset to get rid of it + */ + sdhci_reset(host, SDHCI_RESET_CMD | SDHCI_RESET_DATA); + + return 0; +} + +static u32 sdhci_am654_cqhci_irq(struct sdhci_host *host, u32 intmask) +{ + int cmd_error = 0; + int data_error = 0; + + if (!sdhci_cqe_irq(host, intmask, &cmd_error, &data_error)) + return intmask; + + cqhci_irq(host->mmc, intmask, cmd_error, data_error); + + return 0; +} + static struct sdhci_ops sdhci_am654_ops = { .get_max_clock = sdhci_pltfm_clk_get_max_clock, .get_timeout_clock = sdhci_pltfm_clk_get_max_clock, @@ -248,13 +277,13 @@ static struct sdhci_ops sdhci_am654_ops = { .set_power = sdhci_am654_set_power, .set_clock = sdhci_am654_set_clock, .write_b = sdhci_am654_write_b, + .irq = sdhci_am654_cqhci_irq, .reset = sdhci_reset, }; static const struct sdhci_pltfm_data sdhci_am654_pdata = { .ops = &sdhci_am654_ops, - .quirks = SDHCI_QUIRK_INVERTED_WRITE_PROTECT | - SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12, + .quirks = SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12, .quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN, }; @@ -263,19 +292,6 @@ static const struct sdhci_am654_driver_data sdhci_am654_drvdata = { .flags = IOMUX_PRESENT | FREQSEL_2_BIT | STRBSEL_4_BIT | DLL_PRESENT, }; -static u32 sdhci_am654_cqhci_irq(struct sdhci_host *host, u32 intmask) -{ - int cmd_error = 0; - int data_error = 0; - - if (!sdhci_cqe_irq(host, intmask, &cmd_error, &data_error)) - return intmask; - - cqhci_irq(host->mmc, intmask, cmd_error, data_error); - - return 0; -} - static struct sdhci_ops sdhci_j721e_8bit_ops = { .get_max_clock = sdhci_pltfm_clk_get_max_clock, .get_timeout_clock = sdhci_pltfm_clk_get_max_clock, @@ -290,8 +306,7 @@ static struct sdhci_ops sdhci_j721e_8bit_ops = { static const struct sdhci_pltfm_data sdhci_j721e_8bit_pdata = { .ops = &sdhci_j721e_8bit_ops, - .quirks = SDHCI_QUIRK_INVERTED_WRITE_PROTECT | - SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12, + .quirks = SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12, .quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN, }; @@ -314,8 +329,7 @@ static struct sdhci_ops sdhci_j721e_4bit_ops = { static const struct sdhci_pltfm_data sdhci_j721e_4bit_pdata = { .ops = &sdhci_j721e_4bit_ops, - .quirks = SDHCI_QUIRK_INVERTED_WRITE_PROTECT | - SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12, + .quirks = SDHCI_QUIRK_MULTIBLOCK_READ_ACMD12, .quirks2 = SDHCI_QUIRK2_PRESET_VALUE_BROKEN, }; @@ -549,6 +563,8 @@ static int sdhci_am654_probe(struct platform_device *pdev) goto pm_runtime_put; } + host->mmc_host_ops.execute_tuning = sdhci_am654_execute_tuning; + ret = sdhci_am654_init(host); if (ret) goto pm_runtime_put; diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 4937a088d7d8..fbeb9f73ef28 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -5074,18 +5074,25 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SERVERWORKS, 0x0422, quirk_no_ext_tags); #ifdef CONFIG_PCI_ATS /* - * Some devices have a broken ATS implementation causing IOMMU stalls. - * Don't use ATS for those devices. + * Some devices require additional driver setup to enable ATS. Don't use + * ATS for those devices as ATS will be enabled before the driver has had a + * chance to load and configure the device. */ -static void quirk_no_ats(struct pci_dev *pdev) +static void quirk_amd_harvest_no_ats(struct pci_dev *pdev) { - pci_info(pdev, "disabling ATS (broken on this device)\n"); + if (pdev->device == 0x7340 && pdev->revision != 0xc5) + return; + + pci_info(pdev, "disabling ATS\n"); pdev->ats_cap = 0; } /* AMD Stoney platform GPU */ -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x98e4, quirk_no_ats); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x6900, quirk_no_ats); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x98e4, quirk_amd_harvest_no_ats); +/* AMD Iceland dGPU */ +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x6900, quirk_amd_harvest_no_ats); +/* AMD Navi14 dGPU */ +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x7340, quirk_amd_harvest_no_ats); #endif /* CONFIG_PCI_ATS */ /* Freescale PCIe doesn't support MSI in RC mode */ diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 374db1bd57d1..145d46ba25ae 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -708,8 +708,10 @@ void ceph_mdsc_release_request(struct kref *kref) /* avoid calling iput_final() in mds dispatch threads */ ceph_async_iput(req->r_inode); } - if (req->r_parent) + if (req->r_parent) { ceph_put_cap_refs(ceph_inode(req->r_parent), CEPH_CAP_PIN); + ceph_async_iput(req->r_parent); + } ceph_async_iput(req->r_target_inode); if (req->r_dentry) dput(req->r_dentry); @@ -2676,8 +2678,10 @@ int ceph_mdsc_submit_request(struct ceph_mds_client *mdsc, struct inode *dir, /* take CAP_PIN refs for r_inode, r_parent, r_old_dentry */ if (req->r_inode) ceph_get_cap_refs(ceph_inode(req->r_inode), CEPH_CAP_PIN); - if (req->r_parent) + if (req->r_parent) { ceph_get_cap_refs(ceph_inode(req->r_parent), CEPH_CAP_PIN); + ihold(req->r_parent); + } if (req->r_old_dentry_dir) ceph_get_cap_refs(ceph_inode(req->r_old_dentry_dir), CEPH_CAP_PIN); diff --git a/fs/io_uring.c b/fs/io_uring.c index 187dd94fd6b1..5953d7f13690 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -4463,13 +4463,15 @@ static int io_sqe_files_update(struct io_ring_ctx *ctx, void __user *arg, return -EINVAL; if (copy_from_user(&up, arg, sizeof(up))) return -EFAULT; + if (up.resv) + return -EINVAL; if (check_add_overflow(up.offset, nr_args, &done)) return -EOVERFLOW; if (done > ctx->nr_user_files) return -EINVAL; done = 0; - fds = (__s32 __user *) up.fds; + fds = u64_to_user_ptr(up.fds); while (nr_args) { struct fixed_file_table *table; unsigned index; diff --git a/fs/readdir.c b/fs/readdir.c index d26d5ea4de7b..de2eceffdee8 100644 --- a/fs/readdir.c +++ b/fs/readdir.c @@ -102,10 +102,14 @@ EXPORT_SYMBOL(iterate_dir); * filename length, and the above "soft error" worry means * that it's probably better left alone until we have that * issue clarified. + * + * Note the PATH_MAX check - it's arbitrary but the real + * kernel limit on a possible path component, not NAME_MAX, + * which is the technical standard limit. */ static int verify_dirent_name(const char *name, int len) { - if (!len) + if (len <= 0 || len >= PATH_MAX) return -EIO; if (memchr(name, '/', len)) return -EIO; @@ -206,7 +210,7 @@ struct linux_dirent { struct getdents_callback { struct dir_context ctx; struct linux_dirent __user * current_dir; - struct linux_dirent __user * previous; + int prev_reclen; int count; int error; }; @@ -214,12 +218,13 @@ struct getdents_callback { static int filldir(struct dir_context *ctx, const char *name, int namlen, loff_t offset, u64 ino, unsigned int d_type) { - struct linux_dirent __user * dirent; + struct linux_dirent __user *dirent, *prev; struct getdents_callback *buf = container_of(ctx, struct getdents_callback, ctx); unsigned long d_ino; int reclen = ALIGN(offsetof(struct linux_dirent, d_name) + namlen + 2, sizeof(long)); + int prev_reclen; buf->error = verify_dirent_name(name, namlen); if (unlikely(buf->error)) @@ -232,28 +237,24 @@ static int filldir(struct dir_context *ctx, const char *name, int namlen, buf->error = -EOVERFLOW; return -EOVERFLOW; } - dirent = buf->previous; - if (dirent && signal_pending(current)) + prev_reclen = buf->prev_reclen; + if (prev_reclen && signal_pending(current)) return -EINTR; - - /* - * Note! This range-checks 'previous' (which may be NULL). - * The real range was checked in getdents - */ - if (!user_access_begin(dirent, sizeof(*dirent))) - goto efault; - if (dirent) - unsafe_put_user(offset, &dirent->d_off, efault_end); dirent = buf->current_dir; + prev = (void __user *) dirent - prev_reclen; + if (!user_access_begin(prev, reclen + prev_reclen)) + goto efault; + + /* This might be 'dirent->d_off', but if so it will get overwritten */ + unsafe_put_user(offset, &prev->d_off, efault_end); unsafe_put_user(d_ino, &dirent->d_ino, efault_end); unsafe_put_user(reclen, &dirent->d_reclen, efault_end); unsafe_put_user(d_type, (char __user *) dirent + reclen - 1, efault_end); unsafe_copy_dirent_name(dirent->d_name, name, namlen, efault_end); user_access_end(); - buf->previous = dirent; - dirent = (void __user *)dirent + reclen; - buf->current_dir = dirent; + buf->current_dir = (void __user *)dirent + reclen; + buf->prev_reclen = reclen; buf->count -= reclen; return 0; efault_end: @@ -267,7 +268,6 @@ SYSCALL_DEFINE3(getdents, unsigned int, fd, struct linux_dirent __user *, dirent, unsigned int, count) { struct fd f; - struct linux_dirent __user * lastdirent; struct getdents_callback buf = { .ctx.actor = filldir, .count = count, @@ -285,8 +285,10 @@ SYSCALL_DEFINE3(getdents, unsigned int, fd, error = iterate_dir(f.file, &buf.ctx); if (error >= 0) error = buf.error; - lastdirent = buf.previous; - if (lastdirent) { + if (buf.prev_reclen) { + struct linux_dirent __user * lastdirent; + lastdirent = (void __user *)buf.current_dir - buf.prev_reclen; + if (put_user(buf.ctx.pos, &lastdirent->d_off)) error = -EFAULT; else @@ -299,7 +301,7 @@ SYSCALL_DEFINE3(getdents, unsigned int, fd, struct getdents_callback64 { struct dir_context ctx; struct linux_dirent64 __user * current_dir; - struct linux_dirent64 __user * previous; + int prev_reclen; int count; int error; }; @@ -307,11 +309,12 @@ struct getdents_callback64 { static int filldir64(struct dir_context *ctx, const char *name, int namlen, loff_t offset, u64 ino, unsigned int d_type) { - struct linux_dirent64 __user *dirent; + struct linux_dirent64 __user *dirent, *prev; struct getdents_callback64 *buf = container_of(ctx, struct getdents_callback64, ctx); int reclen = ALIGN(offsetof(struct linux_dirent64, d_name) + namlen + 1, sizeof(u64)); + int prev_reclen; buf->error = verify_dirent_name(name, namlen); if (unlikely(buf->error)) @@ -319,30 +322,27 @@ static int filldir64(struct dir_context *ctx, const char *name, int namlen, buf->error = -EINVAL; /* only used if we fail.. */ if (reclen > buf->count) return -EINVAL; - dirent = buf->previous; - if (dirent && signal_pending(current)) + prev_reclen = buf->prev_reclen; + if (prev_reclen && signal_pending(current)) return -EINTR; - - /* - * Note! This range-checks 'previous' (which may be NULL). - * The real range was checked in getdents - */ - if (!user_access_begin(dirent, sizeof(*dirent))) - goto efault; - if (dirent) - unsafe_put_user(offset, &dirent->d_off, efault_end); dirent = buf->current_dir; + prev = (void __user *)dirent - prev_reclen; + if (!user_access_begin(prev, reclen + prev_reclen)) + goto efault; + + /* This might be 'dirent->d_off', but if so it will get overwritten */ + unsafe_put_user(offset, &prev->d_off, efault_end); unsafe_put_user(ino, &dirent->d_ino, efault_end); unsafe_put_user(reclen, &dirent->d_reclen, efault_end); unsafe_put_user(d_type, &dirent->d_type, efault_end); unsafe_copy_dirent_name(dirent->d_name, name, namlen, efault_end); user_access_end(); - buf->previous = dirent; - dirent = (void __user *)dirent + reclen; - buf->current_dir = dirent; + buf->prev_reclen = reclen; + buf->current_dir = (void __user *)dirent + reclen; buf->count -= reclen; return 0; + efault_end: user_access_end(); efault: @@ -354,7 +354,6 @@ int ksys_getdents64(unsigned int fd, struct linux_dirent64 __user *dirent, unsigned int count) { struct fd f; - struct linux_dirent64 __user * lastdirent; struct getdents_callback64 buf = { .ctx.actor = filldir64, .count = count, @@ -372,9 +371,11 @@ int ksys_getdents64(unsigned int fd, struct linux_dirent64 __user *dirent, error = iterate_dir(f.file, &buf.ctx); if (error >= 0) error = buf.error; - lastdirent = buf.previous; - if (lastdirent) { + if (buf.prev_reclen) { + struct linux_dirent64 __user * lastdirent; typeof(lastdirent->d_off) d_off = buf.ctx.pos; + + lastdirent = (void __user *) buf.current_dir - buf.prev_reclen; if (__put_user(d_off, &lastdirent->d_off)) error = -EFAULT; else diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c index 62b40df36c98..28b241cd6987 100644 --- a/fs/reiserfs/xattr.c +++ b/fs/reiserfs/xattr.c @@ -319,8 +319,12 @@ static int reiserfs_for_each_xattr(struct inode *inode, out_dir: dput(dir); out: - /* -ENODATA isn't an error */ - if (err == -ENODATA) + /* + * -ENODATA: this object doesn't have any xattrs + * -EOPNOTSUPP: this file system doesn't have xattrs enabled on disk. + * Neither are errors + */ + if (err == -ENODATA || err == -EOPNOTSUPP) err = 0; return err; } diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 86eecbd98e84..f73e1775ded0 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -417,6 +417,36 @@ static inline bool xa_marked(const struct xarray *xa, xa_mark_t mark) } /** + * xa_for_each_range() - Iterate over a portion of an XArray. + * @xa: XArray. + * @index: Index of @entry. + * @entry: Entry retrieved from array. + * @start: First index to retrieve from array. + * @last: Last index to retrieve from array. + * + * During the iteration, @entry will have the value of the entry stored + * in @xa at @index. You may modify @index during the iteration if you + * want to skip or reprocess indices. It is safe to modify the array + * during the iteration. At the end of the iteration, @entry will be set + * to NULL and @index will have a value less than or equal to max. + * + * xa_for_each_range() is O(n.log(n)) while xas_for_each() is O(n). You have + * to handle your own locking with xas_for_each(), and if you have to unlock + * after each iteration, it will also end up being O(n.log(n)). + * xa_for_each_range() will spin if it hits a retry entry; if you intend to + * see retry entries, you should use the xas_for_each() iterator instead. + * The xas_for_each() iterator will expand into more inline code than + * xa_for_each_range(). + * + * Context: Any context. Takes and releases the RCU lock. + */ +#define xa_for_each_range(xa, index, entry, start, last) \ + for (index = start, \ + entry = xa_find(xa, &index, last, XA_PRESENT); \ + entry; \ + entry = xa_find_after(xa, &index, last, XA_PRESENT)) + +/** * xa_for_each_start() - Iterate over a portion of an XArray. * @xa: XArray. * @index: Index of @entry. @@ -439,11 +469,8 @@ static inline bool xa_marked(const struct xarray *xa, xa_mark_t mark) * * Context: Any context. Takes and releases the RCU lock. */ -#define xa_for_each_start(xa, index, entry, start) \ - for (index = start, \ - entry = xa_find(xa, &index, ULONG_MAX, XA_PRESENT); \ - entry; \ - entry = xa_find_after(xa, &index, ULONG_MAX, XA_PRESENT)) +#define xa_for_each_start(xa, index, entry, start) \ + xa_for_each_range(xa, index, entry, start, ULONG_MAX) /** * xa_for_each() - Iterate over present entries in an XArray. @@ -508,6 +535,14 @@ static inline bool xa_marked(const struct xarray *xa, xa_mark_t mark) spin_lock_irqsave(&(xa)->xa_lock, flags) #define xa_unlock_irqrestore(xa, flags) \ spin_unlock_irqrestore(&(xa)->xa_lock, flags) +#define xa_lock_nested(xa, subclass) \ + spin_lock_nested(&(xa)->xa_lock, subclass) +#define xa_lock_bh_nested(xa, subclass) \ + spin_lock_bh_nested(&(xa)->xa_lock, subclass) +#define xa_lock_irq_nested(xa, subclass) \ + spin_lock_irq_nested(&(xa)->xa_lock, subclass) +#define xa_lock_irqsave_nested(xa, flags, subclass) \ + spin_lock_irqsave_nested(&(xa)->xa_lock, flags, subclass) /* * Versions of the normal API which require the caller to hold the diff --git a/include/trace/events/xen.h b/include/trace/events/xen.h index 9a0e8af21310..a5ccfa67bc5c 100644 --- a/include/trace/events/xen.h +++ b/include/trace/events/xen.h @@ -66,7 +66,11 @@ TRACE_EVENT(xen_mc_callback, TP_PROTO(xen_mc_callback_fn_t fn, void *data), TP_ARGS(fn, data), TP_STRUCT__entry( - __field(xen_mc_callback_fn_t, fn) + /* + * Use field_struct to avoid is_signed_type() + * comparison of a function pointer. + */ + __field_struct(xen_mc_callback_fn_t, fn) __field(void *, data) ), TP_fast_assign( diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index a3300e1b9a01..55cfcb71606d 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -178,7 +178,8 @@ struct io_uring_params { struct io_uring_files_update { __u32 offset; - __s32 *fds; + __u32 resv; + __aligned_u64 /* __s32 * */ fds; }; #endif diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 26b9168321e7..d65f2d5ab694 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -1147,24 +1147,24 @@ void free_basic_memory_bitmaps(void) void clear_free_pages(void) { -#ifdef CONFIG_PAGE_POISONING_ZERO struct memory_bitmap *bm = free_pages_map; unsigned long pfn; if (WARN_ON(!(free_pages_map))) return; - memory_bm_position_reset(bm); - pfn = memory_bm_next_pfn(bm); - while (pfn != BM_END_OF_MAP) { - if (pfn_valid(pfn)) - clear_highpage(pfn_to_page(pfn)); - + if (IS_ENABLED(CONFIG_PAGE_POISONING_ZERO) || want_init_on_free()) { + memory_bm_position_reset(bm); pfn = memory_bm_next_pfn(bm); + while (pfn != BM_END_OF_MAP) { + if (pfn_valid(pfn)) + clear_highpage(pfn_to_page(pfn)); + + pfn = memory_bm_next_pfn(bm); + } + memory_bm_position_reset(bm); + pr_info("free pages cleared after restore\n"); } - memory_bm_position_reset(bm); - pr_info("free pages cleared after restore\n"); -#endif /* PAGE_POISONING_ZERO */ } /** diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index ddb7e7f5fe8d..5b6ee4aadc26 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -9420,6 +9420,11 @@ __init static int tracing_set_default_clock(void) { /* sched_clock_stable() is determined in late_initcall */ if (!trace_boot_clock && !sched_clock_stable()) { + if (security_locked_down(LOCKDOWN_TRACEFS)) { + pr_warn("Can not set tracing clock due to lockdown\n"); + return -EPERM; + } + printk(KERN_WARNING "Unstable clock detected, switching default tracing clock to \"global\"\n" "If you want to keep using the local clock, then add:\n" diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index f62de5f43e79..6ac35b9e195d 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -116,6 +116,7 @@ struct hist_field { struct ftrace_event_field *field; unsigned long flags; hist_field_fn_t fn; + unsigned int ref; unsigned int size; unsigned int offset; unsigned int is_signed; @@ -1766,11 +1767,13 @@ static struct hist_field *find_var(struct hist_trigger_data *hist_data, struct event_trigger_data *test; struct hist_field *hist_field; + lockdep_assert_held(&event_mutex); + hist_field = find_var_field(hist_data, var_name); if (hist_field) return hist_field; - list_for_each_entry_rcu(test, &file->triggers, list) { + list_for_each_entry(test, &file->triggers, list) { if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { test_data = test->private_data; hist_field = find_var_field(test_data, var_name); @@ -1820,7 +1823,9 @@ static struct hist_field *find_file_var(struct trace_event_file *file, struct event_trigger_data *test; struct hist_field *hist_field; - list_for_each_entry_rcu(test, &file->triggers, list) { + lockdep_assert_held(&event_mutex); + + list_for_each_entry(test, &file->triggers, list) { if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { test_data = test->private_data; hist_field = find_var_field(test_data, var_name); @@ -2423,8 +2428,16 @@ static int contains_operator(char *str) return field_op; } +static void get_hist_field(struct hist_field *hist_field) +{ + hist_field->ref++; +} + static void __destroy_hist_field(struct hist_field *hist_field) { + if (--hist_field->ref > 1) + return; + kfree(hist_field->var.name); kfree(hist_field->name); kfree(hist_field->type); @@ -2466,6 +2479,8 @@ static struct hist_field *create_hist_field(struct hist_trigger_data *hist_data, if (!hist_field) return NULL; + hist_field->ref = 1; + hist_field->hist_data = hist_data; if (flags & HIST_FIELD_FL_EXPR || flags & HIST_FIELD_FL_ALIAS) @@ -2661,6 +2676,17 @@ static struct hist_field *create_var_ref(struct hist_trigger_data *hist_data, { unsigned long flags = HIST_FIELD_FL_VAR_REF; struct hist_field *ref_field; + int i; + + /* Check if the variable already exists */ + for (i = 0; i < hist_data->n_var_refs; i++) { + ref_field = hist_data->var_refs[i]; + if (ref_field->var.idx == var_field->var.idx && + ref_field->var.hist_data == var_field->hist_data) { + get_hist_field(ref_field); + return ref_field; + } + } ref_field = create_hist_field(var_field->hist_data, NULL, flags, NULL); if (ref_field) { @@ -3115,7 +3141,9 @@ static char *find_trigger_filter(struct hist_trigger_data *hist_data, { struct event_trigger_data *test; - list_for_each_entry_rcu(test, &file->triggers, list) { + lockdep_assert_held(&event_mutex); + + list_for_each_entry(test, &file->triggers, list) { if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { if (test->private_data == hist_data) return test->filter_str; @@ -3166,9 +3194,11 @@ find_compatible_hist(struct hist_trigger_data *target_hist_data, struct event_trigger_data *test; unsigned int n_keys; + lockdep_assert_held(&event_mutex); + n_keys = target_hist_data->n_fields - target_hist_data->n_vals; - list_for_each_entry_rcu(test, &file->triggers, list) { + list_for_each_entry(test, &file->triggers, list) { if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { hist_data = test->private_data; @@ -5528,7 +5558,7 @@ static int hist_show(struct seq_file *m, void *v) goto out_unlock; } - list_for_each_entry_rcu(data, &event_file->triggers, list) { + list_for_each_entry(data, &event_file->triggers, list) { if (data->cmd_ops->trigger_type == ETT_EVENT_HIST) hist_trigger_show(m, data, n++); } @@ -5921,7 +5951,9 @@ static int hist_register_trigger(char *glob, struct event_trigger_ops *ops, if (hist_data->attrs->name && !named_data) goto new; - list_for_each_entry_rcu(test, &file->triggers, list) { + lockdep_assert_held(&event_mutex); + + list_for_each_entry(test, &file->triggers, list) { if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { if (!hist_trigger_match(data, test, named_data, false)) continue; @@ -6005,10 +6037,12 @@ static bool have_hist_trigger_match(struct event_trigger_data *data, struct event_trigger_data *test, *named_data = NULL; bool match = false; + lockdep_assert_held(&event_mutex); + if (hist_data->attrs->name) named_data = find_named_trigger(hist_data->attrs->name); - list_for_each_entry_rcu(test, &file->triggers, list) { + list_for_each_entry(test, &file->triggers, list) { if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { if (hist_trigger_match(data, test, named_data, false)) { match = true; @@ -6026,10 +6060,12 @@ static bool hist_trigger_check_refs(struct event_trigger_data *data, struct hist_trigger_data *hist_data = data->private_data; struct event_trigger_data *test, *named_data = NULL; + lockdep_assert_held(&event_mutex); + if (hist_data->attrs->name) named_data = find_named_trigger(hist_data->attrs->name); - list_for_each_entry_rcu(test, &file->triggers, list) { + list_for_each_entry(test, &file->triggers, list) { if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { if (!hist_trigger_match(data, test, named_data, false)) continue; @@ -6051,10 +6087,12 @@ static void hist_unregister_trigger(char *glob, struct event_trigger_ops *ops, struct event_trigger_data *test, *named_data = NULL; bool unregistered = false; + lockdep_assert_held(&event_mutex); + if (hist_data->attrs->name) named_data = find_named_trigger(hist_data->attrs->name); - list_for_each_entry_rcu(test, &file->triggers, list) { + list_for_each_entry(test, &file->triggers, list) { if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { if (!hist_trigger_match(data, test, named_data, false)) continue; @@ -6080,7 +6118,9 @@ static bool hist_file_check_refs(struct trace_event_file *file) struct hist_trigger_data *hist_data; struct event_trigger_data *test; - list_for_each_entry_rcu(test, &file->triggers, list) { + lockdep_assert_held(&event_mutex); + + list_for_each_entry(test, &file->triggers, list) { if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { hist_data = test->private_data; if (check_var_refs(hist_data)) @@ -6323,7 +6363,8 @@ hist_enable_trigger(struct event_trigger_data *data, void *rec, struct enable_trigger_data *enable_data = data->private_data; struct event_trigger_data *test; - list_for_each_entry_rcu(test, &enable_data->file->triggers, list) { + list_for_each_entry_rcu(test, &enable_data->file->triggers, list, + lockdep_is_held(&event_mutex)) { if (test->cmd_ops->trigger_type == ETT_EVENT_HIST) { if (enable_data->enable) test->paused = false; diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index 2cd53ca21b51..40106fff06a4 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -501,7 +501,9 @@ void update_cond_flag(struct trace_event_file *file) struct event_trigger_data *data; bool set_cond = false; - list_for_each_entry_rcu(data, &file->triggers, list) { + lockdep_assert_held(&event_mutex); + + list_for_each_entry(data, &file->triggers, list) { if (data->filter || event_command_post_trigger(data->cmd_ops) || event_command_needs_rec(data->cmd_ops)) { set_cond = true; @@ -536,7 +538,9 @@ static int register_trigger(char *glob, struct event_trigger_ops *ops, struct event_trigger_data *test; int ret = 0; - list_for_each_entry_rcu(test, &file->triggers, list) { + lockdep_assert_held(&event_mutex); + + list_for_each_entry(test, &file->triggers, list) { if (test->cmd_ops->trigger_type == data->cmd_ops->trigger_type) { ret = -EEXIST; goto out; @@ -581,7 +585,9 @@ static void unregister_trigger(char *glob, struct event_trigger_ops *ops, struct event_trigger_data *data; bool unregistered = false; - list_for_each_entry_rcu(data, &file->triggers, list) { + lockdep_assert_held(&event_mutex); + + list_for_each_entry(data, &file->triggers, list) { if (data->cmd_ops->trigger_type == test->cmd_ops->trigger_type) { unregistered = true; list_del_rcu(&data->list); @@ -1497,7 +1503,9 @@ int event_enable_register_trigger(char *glob, struct event_trigger_data *test; int ret = 0; - list_for_each_entry_rcu(test, &file->triggers, list) { + lockdep_assert_held(&event_mutex); + + list_for_each_entry(test, &file->triggers, list) { test_enable_data = test->private_data; if (test_enable_data && (test->cmd_ops->trigger_type == @@ -1537,7 +1545,9 @@ void event_enable_unregister_trigger(char *glob, struct event_trigger_data *data; bool unregistered = false; - list_for_each_entry_rcu(data, &file->triggers, list) { + lockdep_assert_held(&event_mutex); + + list_for_each_entry(data, &file->triggers, list) { enable_data = data->private_data; if (enable_data && (data->cmd_ops->trigger_type == diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 7f890262c8a3..3f54dc2f6e1c 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -290,7 +290,7 @@ static struct trace_kprobe *alloc_trace_kprobe(const char *group, INIT_HLIST_NODE(&tk->rp.kp.hlist); INIT_LIST_HEAD(&tk->rp.kp.list); - ret = trace_probe_init(&tk->tp, event, group); + ret = trace_probe_init(&tk->tp, event, group, false); if (ret < 0) goto error; diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index 905b10af5d5c..9ae87be422f2 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -984,15 +984,19 @@ void trace_probe_cleanup(struct trace_probe *tp) } int trace_probe_init(struct trace_probe *tp, const char *event, - const char *group) + const char *group, bool alloc_filter) { struct trace_event_call *call; + size_t size = sizeof(struct trace_probe_event); int ret = 0; if (!event || !group) return -EINVAL; - tp->event = kzalloc(sizeof(struct trace_probe_event), GFP_KERNEL); + if (alloc_filter) + size += sizeof(struct trace_uprobe_filter); + + tp->event = kzalloc(size, GFP_KERNEL); if (!tp->event) return -ENOMEM; diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index 4ee703728aec..a0ff9e200ef6 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -223,6 +223,12 @@ struct probe_arg { const struct fetch_type *type; /* Type of this argument */ }; +struct trace_uprobe_filter { + rwlock_t rwlock; + int nr_systemwide; + struct list_head perf_events; +}; + /* Event call and class holder */ struct trace_probe_event { unsigned int flags; /* For TP_FLAG_* */ @@ -230,6 +236,7 @@ struct trace_probe_event { struct trace_event_call call; struct list_head files; struct list_head probes; + struct trace_uprobe_filter filter[0]; }; struct trace_probe { @@ -322,7 +329,7 @@ static inline bool trace_probe_has_single_file(struct trace_probe *tp) } int trace_probe_init(struct trace_probe *tp, const char *event, - const char *group); + const char *group, bool alloc_filter); void trace_probe_cleanup(struct trace_probe *tp); int trace_probe_append(struct trace_probe *tp, struct trace_probe *to); void trace_probe_unlink(struct trace_probe *tp); diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 352073d36585..2619bc5ed520 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -34,12 +34,6 @@ struct uprobe_trace_entry_head { #define DATAOF_TRACE_ENTRY(entry, is_return) \ ((void*)(entry) + SIZEOF_TRACE_ENTRY(is_return)) -struct trace_uprobe_filter { - rwlock_t rwlock; - int nr_systemwide; - struct list_head perf_events; -}; - static int trace_uprobe_create(int argc, const char **argv); static int trace_uprobe_show(struct seq_file *m, struct dyn_event *ev); static int trace_uprobe_release(struct dyn_event *ev); @@ -60,7 +54,6 @@ static struct dyn_event_operations trace_uprobe_ops = { */ struct trace_uprobe { struct dyn_event devent; - struct trace_uprobe_filter filter; struct uprobe_consumer consumer; struct path path; struct inode *inode; @@ -351,7 +344,7 @@ alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret) if (!tu) return ERR_PTR(-ENOMEM); - ret = trace_probe_init(&tu->tp, event, group); + ret = trace_probe_init(&tu->tp, event, group, true); if (ret < 0) goto error; @@ -359,7 +352,7 @@ alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret) tu->consumer.handler = uprobe_dispatcher; if (is_ret) tu->consumer.ret_handler = uretprobe_dispatcher; - init_trace_uprobe_filter(&tu->filter); + init_trace_uprobe_filter(tu->tp.event->filter); return tu; error: @@ -1067,13 +1060,14 @@ static void __probe_event_disable(struct trace_probe *tp) struct trace_probe *pos; struct trace_uprobe *tu; + tu = container_of(tp, struct trace_uprobe, tp); + WARN_ON(!uprobe_filter_is_empty(tu->tp.event->filter)); + list_for_each_entry(pos, trace_probe_probe_list(tp), list) { tu = container_of(pos, struct trace_uprobe, tp); if (!tu->inode) continue; - WARN_ON(!uprobe_filter_is_empty(&tu->filter)); - uprobe_unregister(tu->inode, tu->offset, &tu->consumer); tu->inode = NULL; } @@ -1108,7 +1102,7 @@ static int probe_event_enable(struct trace_event_call *call, } tu = container_of(tp, struct trace_uprobe, tp); - WARN_ON(!uprobe_filter_is_empty(&tu->filter)); + WARN_ON(!uprobe_filter_is_empty(tu->tp.event->filter)); if (enabled) return 0; @@ -1205,39 +1199,39 @@ __uprobe_perf_filter(struct trace_uprobe_filter *filter, struct mm_struct *mm) } static inline bool -uprobe_filter_event(struct trace_uprobe *tu, struct perf_event *event) +trace_uprobe_filter_event(struct trace_uprobe_filter *filter, + struct perf_event *event) { - return __uprobe_perf_filter(&tu->filter, event->hw.target->mm); + return __uprobe_perf_filter(filter, event->hw.target->mm); } -static int uprobe_perf_close(struct trace_uprobe *tu, struct perf_event *event) +static bool trace_uprobe_filter_remove(struct trace_uprobe_filter *filter, + struct perf_event *event) { bool done; - write_lock(&tu->filter.rwlock); + write_lock(&filter->rwlock); if (event->hw.target) { list_del(&event->hw.tp_list); - done = tu->filter.nr_systemwide || + done = filter->nr_systemwide || (event->hw.target->flags & PF_EXITING) || - uprobe_filter_event(tu, event); + trace_uprobe_filter_event(filter, event); } else { - tu->filter.nr_systemwide--; - done = tu->filter.nr_systemwide; + filter->nr_systemwide--; + done = filter->nr_systemwide; } - write_unlock(&tu->filter.rwlock); + write_unlock(&filter->rwlock); - if (!done) - return uprobe_apply(tu->inode, tu->offset, &tu->consumer, false); - - return 0; + return done; } -static int uprobe_perf_open(struct trace_uprobe *tu, struct perf_event *event) +/* This returns true if the filter always covers target mm */ +static bool trace_uprobe_filter_add(struct trace_uprobe_filter *filter, + struct perf_event *event) { bool done; - int err; - write_lock(&tu->filter.rwlock); + write_lock(&filter->rwlock); if (event->hw.target) { /* * event->parent != NULL means copy_process(), we can avoid @@ -1247,28 +1241,21 @@ static int uprobe_perf_open(struct trace_uprobe *tu, struct perf_event *event) * attr.enable_on_exec means that exec/mmap will install the * breakpoints we need. */ - done = tu->filter.nr_systemwide || + done = filter->nr_systemwide || event->parent || event->attr.enable_on_exec || - uprobe_filter_event(tu, event); - list_add(&event->hw.tp_list, &tu->filter.perf_events); + trace_uprobe_filter_event(filter, event); + list_add(&event->hw.tp_list, &filter->perf_events); } else { - done = tu->filter.nr_systemwide; - tu->filter.nr_systemwide++; + done = filter->nr_systemwide; + filter->nr_systemwide++; } - write_unlock(&tu->filter.rwlock); + write_unlock(&filter->rwlock); - err = 0; - if (!done) { - err = uprobe_apply(tu->inode, tu->offset, &tu->consumer, true); - if (err) - uprobe_perf_close(tu, event); - } - return err; + return done; } -static int uprobe_perf_multi_call(struct trace_event_call *call, - struct perf_event *event, - int (*op)(struct trace_uprobe *tu, struct perf_event *event)) +static int uprobe_perf_close(struct trace_event_call *call, + struct perf_event *event) { struct trace_probe *pos, *tp; struct trace_uprobe *tu; @@ -1278,25 +1265,59 @@ static int uprobe_perf_multi_call(struct trace_event_call *call, if (WARN_ON_ONCE(!tp)) return -ENODEV; + tu = container_of(tp, struct trace_uprobe, tp); + if (trace_uprobe_filter_remove(tu->tp.event->filter, event)) + return 0; + list_for_each_entry(pos, trace_probe_probe_list(tp), list) { tu = container_of(pos, struct trace_uprobe, tp); - ret = op(tu, event); + ret = uprobe_apply(tu->inode, tu->offset, &tu->consumer, false); if (ret) break; } return ret; } + +static int uprobe_perf_open(struct trace_event_call *call, + struct perf_event *event) +{ + struct trace_probe *pos, *tp; + struct trace_uprobe *tu; + int err = 0; + + tp = trace_probe_primary_from_call(call); + if (WARN_ON_ONCE(!tp)) + return -ENODEV; + + tu = container_of(tp, struct trace_uprobe, tp); + if (trace_uprobe_filter_add(tu->tp.event->filter, event)) + return 0; + + list_for_each_entry(pos, trace_probe_probe_list(tp), list) { + err = uprobe_apply(tu->inode, tu->offset, &tu->consumer, true); + if (err) { + uprobe_perf_close(call, event); + break; + } + } + + return err; +} + static bool uprobe_perf_filter(struct uprobe_consumer *uc, enum uprobe_filter_ctx ctx, struct mm_struct *mm) { + struct trace_uprobe_filter *filter; struct trace_uprobe *tu; int ret; tu = container_of(uc, struct trace_uprobe, consumer); - read_lock(&tu->filter.rwlock); - ret = __uprobe_perf_filter(&tu->filter, mm); - read_unlock(&tu->filter.rwlock); + filter = tu->tp.event->filter; + + read_lock(&filter->rwlock); + ret = __uprobe_perf_filter(filter, mm); + read_unlock(&filter->rwlock); return ret; } @@ -1419,10 +1440,10 @@ trace_uprobe_register(struct trace_event_call *event, enum trace_reg type, return 0; case TRACE_REG_PERF_OPEN: - return uprobe_perf_multi_call(event, data, uprobe_perf_open); + return uprobe_perf_open(event, data); case TRACE_REG_PERF_CLOSE: - return uprobe_perf_multi_call(event, data, uprobe_perf_close); + return uprobe_perf_close(event, data); #endif default: diff --git a/lib/strncpy_from_user.c b/lib/strncpy_from_user.c index dccb95af6003..706020b06617 100644 --- a/lib/strncpy_from_user.c +++ b/lib/strncpy_from_user.c @@ -30,13 +30,6 @@ static inline long do_strncpy_from_user(char *dst, const char __user *src, const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS; unsigned long res = 0; - /* - * Truncate 'max' to the user-specified limit, so that - * we only have one limit we need to check in the loop - */ - if (max > count) - max = count; - if (IS_UNALIGNED(src, dst)) goto byte_at_a_time; @@ -114,6 +107,13 @@ long strncpy_from_user(char *dst, const char __user *src, long count) unsigned long max = max_addr - src_addr; long retval; + /* + * Truncate 'max' to the user-specified limit, so that + * we only have one limit we need to check in the loop + */ + if (max > count) + max = count; + kasan_check_write(dst, count); check_object_size(dst, count, false); if (user_access_begin(src, max)) { diff --git a/lib/strnlen_user.c b/lib/strnlen_user.c index 6c0005d5dd5c..41670d4a5816 100644 --- a/lib/strnlen_user.c +++ b/lib/strnlen_user.c @@ -27,13 +27,6 @@ static inline long do_strnlen_user(const char __user *src, unsigned long count, unsigned long c; /* - * Truncate 'max' to the user-specified limit, so that - * we only have one limit we need to check in the loop - */ - if (max > count) - max = count; - - /* * Do everything aligned. But that means that we * need to also expand the maximum.. */ @@ -109,6 +102,13 @@ long strnlen_user(const char __user *str, long count) unsigned long max = max_addr - src_addr; long retval; + /* + * Truncate 'max' to the user-specified limit, so that + * we only have one limit we need to check in the loop + */ + if (max > count) + max = count; + if (user_access_begin(str, max)) { retval = do_strnlen_user(str, count, max); user_access_end(); diff --git a/lib/test_xarray.c b/lib/test_xarray.c index 7df4f7f395bf..55c14e8c8859 100644 --- a/lib/test_xarray.c +++ b/lib/test_xarray.c @@ -2,6 +2,7 @@ /* * test_xarray.c: Test the XArray API * Copyright (c) 2017-2018 Microsoft Corporation + * Copyright (c) 2019-2020 Oracle * Author: Matthew Wilcox <[email protected]> */ @@ -902,28 +903,34 @@ static noinline void check_store_iter(struct xarray *xa) XA_BUG_ON(xa, !xa_empty(xa)); } -static noinline void check_multi_find(struct xarray *xa) +static noinline void check_multi_find_1(struct xarray *xa, unsigned order) { #ifdef CONFIG_XARRAY_MULTI + unsigned long multi = 3 << order; + unsigned long next = 4 << order; unsigned long index; - xa_store_order(xa, 12, 2, xa_mk_value(12), GFP_KERNEL); - XA_BUG_ON(xa, xa_store_index(xa, 16, GFP_KERNEL) != NULL); + xa_store_order(xa, multi, order, xa_mk_value(multi), GFP_KERNEL); + XA_BUG_ON(xa, xa_store_index(xa, next, GFP_KERNEL) != NULL); + XA_BUG_ON(xa, xa_store_index(xa, next + 1, GFP_KERNEL) != NULL); index = 0; XA_BUG_ON(xa, xa_find(xa, &index, ULONG_MAX, XA_PRESENT) != - xa_mk_value(12)); - XA_BUG_ON(xa, index != 12); - index = 13; + xa_mk_value(multi)); + XA_BUG_ON(xa, index != multi); + index = multi + 1; XA_BUG_ON(xa, xa_find(xa, &index, ULONG_MAX, XA_PRESENT) != - xa_mk_value(12)); - XA_BUG_ON(xa, (index < 12) || (index >= 16)); + xa_mk_value(multi)); + XA_BUG_ON(xa, (index < multi) || (index >= next)); XA_BUG_ON(xa, xa_find_after(xa, &index, ULONG_MAX, XA_PRESENT) != - xa_mk_value(16)); - XA_BUG_ON(xa, index != 16); - - xa_erase_index(xa, 12); - xa_erase_index(xa, 16); + xa_mk_value(next)); + XA_BUG_ON(xa, index != next); + XA_BUG_ON(xa, xa_find_after(xa, &index, next, XA_PRESENT) != NULL); + XA_BUG_ON(xa, index != next); + + xa_erase_index(xa, multi); + xa_erase_index(xa, next); + xa_erase_index(xa, next + 1); XA_BUG_ON(xa, !xa_empty(xa)); #endif } @@ -1046,12 +1053,33 @@ static noinline void check_find_3(struct xarray *xa) xa_destroy(xa); } +static noinline void check_find_4(struct xarray *xa) +{ + unsigned long index = 0; + void *entry; + + xa_store_index(xa, ULONG_MAX, GFP_KERNEL); + + entry = xa_find_after(xa, &index, ULONG_MAX, XA_PRESENT); + XA_BUG_ON(xa, entry != xa_mk_index(ULONG_MAX)); + + entry = xa_find_after(xa, &index, ULONG_MAX, XA_PRESENT); + XA_BUG_ON(xa, entry); + + xa_erase_index(xa, ULONG_MAX); +} + static noinline void check_find(struct xarray *xa) { + unsigned i; + check_find_1(xa); check_find_2(xa); check_find_3(xa); - check_multi_find(xa); + check_find_4(xa); + + for (i = 2; i < 10; i++) + check_multi_find_1(xa, i); check_multi_find_2(xa); } @@ -1132,6 +1160,27 @@ static noinline void check_move_tiny(struct xarray *xa) XA_BUG_ON(xa, !xa_empty(xa)); } +static noinline void check_move_max(struct xarray *xa) +{ + XA_STATE(xas, xa, 0); + + xa_store_index(xa, ULONG_MAX, GFP_KERNEL); + rcu_read_lock(); + XA_BUG_ON(xa, xas_find(&xas, ULONG_MAX) != xa_mk_index(ULONG_MAX)); + XA_BUG_ON(xa, xas_find(&xas, ULONG_MAX) != NULL); + rcu_read_unlock(); + + xas_set(&xas, 0); + rcu_read_lock(); + XA_BUG_ON(xa, xas_find(&xas, ULONG_MAX) != xa_mk_index(ULONG_MAX)); + xas_pause(&xas); + XA_BUG_ON(xa, xas_find(&xas, ULONG_MAX) != NULL); + rcu_read_unlock(); + + xa_erase_index(xa, ULONG_MAX); + XA_BUG_ON(xa, !xa_empty(xa)); +} + static noinline void check_move_small(struct xarray *xa, unsigned long idx) { XA_STATE(xas, xa, 0); @@ -1240,6 +1289,7 @@ static noinline void check_move(struct xarray *xa) xa_destroy(xa); check_move_tiny(xa); + check_move_max(xa); for (i = 0; i < 16; i++) check_move_small(xa, 1UL << i); diff --git a/lib/xarray.c b/lib/xarray.c index 1237c213f52b..1d9fab7db8da 100644 --- a/lib/xarray.c +++ b/lib/xarray.c @@ -1,7 +1,8 @@ // SPDX-License-Identifier: GPL-2.0+ /* * XArray implementation - * Copyright (c) 2017 Microsoft Corporation + * Copyright (c) 2017-2018 Microsoft Corporation + * Copyright (c) 2018-2020 Oracle * Author: Matthew Wilcox <[email protected]> */ @@ -967,6 +968,7 @@ void xas_pause(struct xa_state *xas) if (xas_invalid(xas)) return; + xas->xa_node = XAS_RESTART; if (node) { unsigned int offset = xas->xa_offset; while (++offset < XA_CHUNK_SIZE) { @@ -974,10 +976,11 @@ void xas_pause(struct xa_state *xas) break; } xas->xa_index += (offset - xas->xa_offset) << node->shift; + if (xas->xa_index == 0) + xas->xa_node = XAS_BOUNDS; } else { xas->xa_index++; } - xas->xa_node = XAS_RESTART; } EXPORT_SYMBOL_GPL(xas_pause); @@ -1079,13 +1082,15 @@ void *xas_find(struct xa_state *xas, unsigned long max) { void *entry; - if (xas_error(xas)) + if (xas_error(xas) || xas->xa_node == XAS_BOUNDS) return NULL; + if (xas->xa_index > max) + return set_bounds(xas); if (!xas->xa_node) { xas->xa_index = 1; return set_bounds(xas); - } else if (xas_top(xas->xa_node)) { + } else if (xas->xa_node == XAS_RESTART) { entry = xas_load(xas); if (entry || xas_not_node(xas->xa_node)) return entry; @@ -1150,6 +1155,8 @@ void *xas_find_marked(struct xa_state *xas, unsigned long max, xa_mark_t mark) if (xas_error(xas)) return NULL; + if (xas->xa_index > max) + goto max; if (!xas->xa_node) { xas->xa_index = 1; @@ -1824,6 +1831,17 @@ void *xa_find(struct xarray *xa, unsigned long *indexp, } EXPORT_SYMBOL(xa_find); +static bool xas_sibling(struct xa_state *xas) +{ + struct xa_node *node = xas->xa_node; + unsigned long mask; + + if (!node) + return false; + mask = (XA_CHUNK_SIZE << node->shift) - 1; + return (xas->xa_index & mask) > (xas->xa_offset << node->shift); +} + /** * xa_find_after() - Search the XArray for a present entry. * @xa: XArray. @@ -1847,21 +1865,20 @@ void *xa_find_after(struct xarray *xa, unsigned long *indexp, XA_STATE(xas, xa, *indexp + 1); void *entry; + if (xas.xa_index == 0) + return NULL; + rcu_read_lock(); for (;;) { if ((__force unsigned int)filter < XA_MAX_MARKS) entry = xas_find_marked(&xas, max, filter); else entry = xas_find(&xas, max); - if (xas.xa_node == XAS_BOUNDS) + + if (xas_invalid(&xas)) break; - if (xas.xa_shift) { - if (xas.xa_index & ((1UL << xas.xa_shift) - 1)) - continue; - } else { - if (xas.xa_offset < (xas.xa_index & XA_CHUNK_MASK)) - continue; - } + if (xas_sibling(&xas)) + continue; if (!xas_retry(&xas, entry)) break; } |